> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Configure Plugins

## Docs

- [Configure Plugins](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/about.md): Configure built-in and discoverable NeMo Relay plugins with plugins.toml.
- [Observability](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/observability/about.md): Configure NeMo Relay observability exporters for events, traces, logs, metrics, and trajectories.
- [Configuration](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/observability/configuration.md): Configure the built-in NeMo Relay observability plugin.
- [Agent Trajectory Interchange Format (ATIF)](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/observability/atif.md): Configure ATIF trajectory export to local files, HTTP endpoints, or S3-compatible storage.
- [Agent Trajectory Observability Format (ATOF)](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/observability/atof.md): Configure raw ATOF event export to JSONL files and stream sinks.
- [OpenTelemetry](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/observability/opentelemetry.md): Export NeMo Relay traces, logs, and metrics through OpenTelemetry Protocol endpoints.
- [OpenInference](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/observability/openinference.md): Export OpenInference-compatible traces through an OpenTelemetry endpoint.
- [Adaptive](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/adaptive/about.md): Configure the built-in Adaptive plugin for measured runtime tuning.
- [Adaptive Configuration](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/adaptive/configuration.md): Configure the Adaptive component, including state, telemetry, hints, ACG, and response caching.
- [Adaptive Cache Governor (ACG)](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/adaptive/acg.md): Configure Adaptive Cache Governor for provider-aware prompt-cache planning.
- [Adaptive Hints](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/adaptive/adaptive-hints.md): Configure Adaptive Hints to add guidance metadata to managed LLM requests.
- [Response Cache](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/adaptive/response-cache.md): Configure exact-match response caching for managed LLM calls and tool results.
- [NeMo Guardrails (Deprecated)](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/nemo-guardrails/about.md): Review the deprecated built-in NeMo Guardrails plugin for managed LLM and tool execution.
- [NeMo Guardrails Configuration](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/nemo-guardrails/configuration.md): Configure the deprecated built-in remote and local NeMo Guardrails backends.
- [PII Redaction Plugin](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/pii-redaction/about.md): Configure built-in PII redaction for emitted NeMo Relay observability payloads.
- [PII Redaction Configuration](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/pii-redaction/configuration.md): Configure PII redaction actions, detectors, targets, and backend modes.
- [Model Pricing](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/model-pricing.md): Configure file and inline pricing catalogs for LLM cost estimates.
- [Configure Discoverable Plugins](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/discoverable-plugins.md): Install, validate, trust, and configure manifest-backed NeMo Relay plugins.
- [Plugin Configuration Files](https://docs.nvidia.com/nemo/relay/v0.8.4/configure-plugins/plugin-configuration-files.md): Configure plugins.toml discovery, layering, validation, and interactive editing.